Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3488 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1381197 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.4107. Min Act: -0.0000

Data Index: 923793 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1879047 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1540576 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1450697 (The Pile)

Max Activating Token Index: 721

Text #5

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3461. Min Act: -0.0000

Data Index: 376548 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3240. Min Act: -0.0000

Data Index: 624219 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3735. Min Act: -0.0000

Data Index: 832857 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3206. Min Act: -0.0000

Data Index: 638647 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1647187 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1317563 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3171. Min Act: -0.0000

Data Index: 663741 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1546295 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3141. Min Act: -0.0000

Data Index: 22616 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3041. Min Act: -0.0000

Data Index: 120972 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.3001. Min Act: -0.0000

Data Index: 34904 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1065729 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.2962. Min Act: -0.0000

Data Index: 150278 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.2898. Min Act: -0.0000

Data Index: 341378 (The Pile)

Max Activating Token Index: 749

Text #19

Max Range: 0.4323. Min Range: -0.4323

Max Act: 0.2951. Min Act: -0.0000

Data Index: 316950 (The Pile)

Max Activating Token Index: 733